create-agentic-workflow
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a Python script via Bash using arguments derived from user input such as the skill directory and trigger list. This pattern presents a risk of command injection if the input strings contain malicious shell meta-characters.
- [PROMPT_INJECTION]: The skill processes content from existing skills which introduces an indirect prompt injection vulnerability.
- Ingestion points: Content is read from the directory path provided by the user (target-skill).
- Boundary markers: No explicit delimiters are used to encapsulate or ignore instructions within the ingested files.
- Capability inventory: The skill has access to Bash for executing subprocesses and Write for modifying the filesystem.
- Sanitization: There are no instructions for validating or sanitizing the content of the target skill files during the conversion process.
Audit Metadata